Prevention of Cooktop Ignition Using Detection and Multi-Step Machine Learning Algorithms.

This paper presents a study to examine the potential use of machine learning models to build a real-time detection algorithm for prevention of kitchen cooktop fires. Sixteen sets of time-dependent sensor signals were obtained from 60 normal/ignition cooking experiments. A total of 200 000 data instances are documented and analyzed. The raw data are preprocessed. Selected features are generated for time series data focusing on real-time detection applications. Utilizing the leave-one-out cross validation method, three machine learning models are built and tested. Parametric studies are carried out to understand the diversity, volume, and tendency of the data. Given the current dataset, the detection algorithm based on Support Vector Machine (SVM) provides the most reliable prediction (with an overall accuracy of 96.9 %) on pre-ignition conditions. Analyses indicate that using a multi-step approach can further improve overall prediction accuracy. The development of an accurate detection algorithm can provide reliable feedback to intercept ignition of unattended cooking and help reduce fire losses.

P-Flash - A Machine Learning-based Model for Flashover Prediction using Recovered Temperature Data.

Research was conducted to examine the use of Support Vector Regression (SVR) to build a model to forecast the potential occurrence of flashover in a single-floor, multi-room compartment fire. Synthetic temperature data for heat detectors in different rooms were generated, 1000 simulation cases are considered, and a total of 8 million data points are utilized for model development. An operating temperature limitation is placed on heat detectors where they fail at a fixed exposure temperature of 150 °C and no longer provide data to more closely follow actual performance. The forecast model P-Flash (Prediction model for Flashover occurrence) is developed to use an array of heat detector temperature data, including in adjacent spaces, to recover temperature data from the room of fire origin and predict potential for flashover. Two special treatments, sequence segmentation and learning from fitting, are proposed to overcome the temperature limitation of heat detectors in real-life fire scenarios and to enhance prediction capabilities to determine if the flashover condition is met even with situations where there is no temperature data from all detectors. Experimental evaluation shows that P-Flash offers reliable prediction. The model performance is approximately 83 % and 81 %, respectively, for current and future flashover occurrence, considering heat detector failure at 150 °C. Results demonstrate that P-Flash, a new data-driven model, has potential to provide fire fighters real-time, trustworthy, and actionable information to enhance situational awareness, operational effectiveness, and safety for firefighting.

Generating Synthetic Sensor Data to Facilitate Machine Learning Paradigm for Prediction of Building Fire Hazard.

Using the zone fire model CFAST as the simulation engine, time series data for building sensors, such as heat detectors, smoke detectors, and other targets at any arbitrary locations in multi-room compartments with different geometric configurations, can be obtained. An automated process for creating inputs files and summarizing model results, CData, is being developed as a companion to CFAST. An example case is presented to demonstrate the use of CData where synthetic data is generated for a wide range of fire scenarios. Three machine learning algorithms: support vector machine (SVM), decision tree (DT), and random forest (RF), are used to develop classification models that can predict the location of a fire based on temperature data within a compartment. Results show that DT and RF have excellent performance on the prediction of fire location and achieve model accuracy in between 93 % and 96 %. For SVM, model performance is sensitive to the size of training data. Additional study shows that results obtained from DT and RT can be used to examine the importance of each input feature. This paper contributes a learning-by-synthesis approach to facilitate the utilization of a machine learning paradigm to enhance situational awareness for fire fighting in buildings.